Implement HostVector for more robust CPU <-> GPU data transfers#93
Merged
Implement HostVector for more robust CPU <-> GPU data transfers#93
Conversation
Contributor
Benchmark Results (Julia v1)Time benchmarks
Memory benchmarks
|
Codecov Report❌ Patch coverage is Additional details and impacted files@@ Coverage Diff @@
## master #93 +/- ##
==========================================
- Coverage 93.32% 92.98% -0.34%
==========================================
Files 122 126 +4
Lines 8280 8407 +127
==========================================
+ Hits 7727 7817 +90
- Misses 553 590 +37 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This is used as a staging area in CPU memory during host-device transfers, which is pagelocked on CUDA and AMDGPU for faster transfers. We also avoid as much as possible reallocating this CPU memory (typically when the number of filament points changes), which would require redoing the pagelock. This seemed to cause crashes in AMDGPU in particular which seem to be fixed now. Moreover, the multi-GPU behaviour is more robust now (in CUDA in particular, where there were some issues).